© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 83185
    Prev
    Next
    INDEX
    Explanations

    phrases relating to totality or completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .scalablytyped
    -0.07
     aggress
    -0.06
    å¤ļ
    -0.06
    oltip
    -0.06
     insign
    -0.06
    aft
    -0.06
    èĩ³
    -0.06
    imo
    -0.06
     Recon
    -0.06
    æģµ
    -0.06
    POSITIVE LOGITS
     entirely
    0.10
     completely
    0.07
     Gree
    0.07
    eree
    0.07
    ssa
    0.07
    ape
    0.07
     useClass
    0.07
    lluminate
    0.07
    erral
    0.07
     except
    0.06
    Activations Density 0.025%

    No Known Activations